Chi-Square Testing 10/23/2012. Readings Chapter 7 Tests of Significance and Measures of Association (Pollock) (pp. 155-169) Chapter 5 Making Controlled.

Slides:



Advertisements
Similar presentations
Tests of Significance and Measures of Association
Advertisements

Chapter 13 (Ch. 11 in 2nd Can. Ed.)
POL242 October 9 and 11, 2012 Jennifer Hove. Questions of Causality Recall: Most causal thinking in social sciences is probabilistic, not deterministic:
1. Nominal Measures of Association 2. Ordinal Measure s of Association
Association Between Two Variables Measured at the Nominal Level
Measures of Association for contingency tables 4 Figure 8.2 : lambda – association; +-1: strong; near 0: weak Positive association: as value of the independent.
Univariate Statistics 9/18/2012. Readings Chapter 2 Measuring and Describing Variables (Pollock) (pp.32-33) Chapter 2 Descriptive Statistics (Pollock.
Bivariate Analysis Cross-tabulation and chi-square.
Three important questions Three important questions to ask: 1. Whether column % change? 2. Is the relationship significant? (.05 as chi square significance.
Chapter 11 Contingency Table Analysis. Nonparametric Systems Another method of examining the relationship between independent (X) and dependant (Y) variables.
CJ 526 Statistical Analysis in Criminal Justice
PPA 415 – Research Methods in Public Administration Lecture 9 – Bivariate Association.
Chi-square Test of Independence
Intro to Statistics for the Behavioral Sciences PSYC 1900 Lecture 17: Chi-Square.
PSY 307 – Statistics for the Behavioral Sciences Chapter 19 – Chi-Square Test for Qualitative Data Chapter 21 – Deciding Which Test to Use.
PPA 501 – Analytical Methods in Administration Lecture 9 – Bivariate Association.
Summary of Quantitative Analysis Neuman and Robson Ch. 11
Skewness 9/27/2012. Readings Chapter 2 Measuring and Describing Variables (Pollock) (pp.37-44) Chapter 6. Foundations of Statistical Inference ( )
Crosstabs. When to Use Crosstabs as a Bivariate Data Analysis Technique For examining the relationship of two CATEGORIC variables  For example, do men.
Review Regression and Pearson’s R SPSS Demo
Chapter 14 in 1e Ch. 12 in 2/3 Can. Ed. Association Between Variables Measured at the Ordinal Level Using the Statistic Gamma and Conducting a Z-test for.
Inferential Statistics
Correlations 11/5/2013. BSS Career Fair Wednesday 11/6/2013- Mabee A & B 12:30-2:30P.
Week 11 Chapter 12 – Association between variables measured at the nominal level.
Measures of Dispersion 9/26/2013. Readings Chapter 2 Measuring and Describing Variables (Pollock) (pp.37-44) Chapter 6. Foundations of Statistical Inference.
Significance Testing 10/22/2013. Readings Chapter 3 Proposing Explanations, Framing Hypotheses, and Making Comparisons (Pollock) (pp ) Chapter 5.
Cross Tabulation and Chi-Square Testing. Cross-Tabulation While a frequency distribution describes one variable at a time, a cross-tabulation describes.
Association between Variables Measured at the Nominal Level.
Correlations 11/7/2013. Readings Chapter 8 Correlation and Linear Regression (Pollock) (pp ) Chapter 8 Correlation and Regression (Pollock Workbook)
Significance Testing 10/15/2013. Readings Chapter 3 Proposing Explanations, Framing Hypotheses, and Making Comparisons (Pollock) (pp ) Chapter 5.
Bivariate Relationships Analyzing two variables at a time, usually the Independent & Dependent Variables Like one variable at a time, this can be done.
1 Psych 5500/6500 Chi-Square (Part Two) Test for Association Fall, 2008.
Variables 9/12/2013. Readings Chapter 2 Measuring and Describing Variables (Pollock) (pp.32-33) Chapter 2 Descriptive Statistics (Pollock Workbook)
CJ 526 Statistical Analysis in Criminal Justice
Chi-Square Test of Independence Practice Problem – 1
Measures of Association. When examining relationships (or the lack thereof) between nominal- and ordinal-level variables, Crosstabs are our instruments.
Multivariate Regression and Data Collection 11/21/2013.
Tests of Significance June 11, 2008 Ivan Katchanovski, Ph.D. POL 242Y-Y.
Chi-square (χ 2 ) Fenster Chi-Square Chi-Square χ 2 Chi-Square χ 2 Tests of Statistical Significance for Nominal Level Data (Note: can also be used for.
Skewness and Curves 10/1/2013. Readings Chapter 2 Measuring and Describing Variables (Pollock) (pp.37-44) Chapter 6. Foundations of Statistical Inference.
Cross-Tabs With Ordinal Variables 10/31/2013. BSS Career Fair Wednesday 11/6/2013- Mabee A & B Who will be there?there? More InformationInformation.
Multivariate Regression 11/19/2013. Readings Chapter 8 (pp ) Chapter 9 Dummy Variables and Interaction Effects (Pollock Workbook)
Cross-Tabs With Nominal Variables 10/24/2013. Readings Chapter 7 Tests of Significance and Measures of Association (Pollock) (pp ) Chapter 5 Making.
Social Science Research Design and Statistics, 2/e Alfred P. Rovai, Jason D. Baker, and Michael K. Ponton Pearson Chi-Square Contingency Table Analysis.
Overview Chi-square showed us how to determine whether two (nominal or ordinal) variables are statistically significantly related to each other. But statistical.
Research Design 10/16/2012. Readings Chapter 3 Proposing Explanations, Framing Hypotheses, and Making Comparisons (pp ) Chapter 5 Making Controlled.
Statistical Significance. Office Hour Sign Up I’d like to meet with everybody 1 on 1 re papers Please sign up during office hours, or let me know If those.
Lecture 15: Crosstabulation 1 Sociology 5811 Copyright © 2005 by Evan Schofer Do not copy or distribute without permission.
Hypotheses 9/4/2012. Readings Chapter 1 The Measurement of Concepts (14- 23) (Pollock) Chapter 2 Measuring and Describing Variables (Pollock) (pp.28-31)
Chapter 11, 12, 13, 14 and 16 Association at Nominal and Ordinal Level The Procedure in Steps.
Correlation 11/1/2012. Readings Chapter 8 Correlation and Linear Regression (Pollock) (pp ) Chapter 8 Correlation and Regression (Pollock Workbook)
Practice Problem: Lambda (1)
Chapter 15 The Chi-Square Statistic: Tests for Goodness of Fit and Independence PowerPoint Lecture Slides Essentials of Statistics for the Behavioral.
Copyright © 2014 by Nelson Education Limited Chapter 11 Introduction to Bivariate Association and Measures of Association for Variables Measured.
Chapter 14 – 1 Chi-Square Chi-Square as a Statistical Test Statistical Independence Hypothesis Testing with Chi-Square The Assumptions Stating the Research.
Ch 13: Chi-square tests Part 2: Nov 29, Chi-sq Test for Independence Deals with 2 nominal variables Create ‘contingency tables’ –Crosses the 2 variables.
Class Seven Turn In: Chapter 18: 32, 34, 36 Chapter 19: 26, 34, 44 Quiz 3 For Class Eight: Chapter 20: 18, 20, 24 Chapter 22: 34, 36 Read Chapters 23 &
Final Project Reminder
Final Project Reminder
Chapter 14 in 1e Ch. 12 in 2/3 Can. Ed.
Chapter 13 (1e), (Ch. 11 2/3e) Association Between Variables Measured at the Nominal Level: Phi, Cramer’s V, and Lambda.
Association Between Variables Measured at Nominal Level
The Chi-Square Distribution and Test for Independence
Inference for Categorical Data
Hypothesis Testing and Comparing Two Proportions
Chapter 10 Analyzing the Association Between Categorical Variables
1. Nominal Measures of Association 2. Ordinal Measure s of Associaiton
Contingency Tables (cross tabs)
1. Nominal Measures of Association 2. Ordinal Measure s of Associaiton
Presentation transcript:

Chi-Square Testing 10/23/2012

Readings Chapter 7 Tests of Significance and Measures of Association (Pollock) (pp ) Chapter 5 Making Controlled Comparisons (Pollock Workbook) Chapter 7 Chi-Square and Measures of Association (Pollock Workbook)

OPPORTUNITIES TO DISCUSS COURSE CONTENT

Office Hours For the Week When – Thursday 8-12 – Wednesday 11-1 – And appointment The endorsementendorsement

Course Learning Objectives Students will learn the research methods commonly used in behavioral sciences and will be able to interpret and explain empirical data. Students will learn the basics of research design and be able to critically analyze the advantages and disadvantages of different types of design. As this course fulfills the Computational Skills portion of the University degree plan, students will achieve competency in conducting statistical data analysis using the SPSS software program.

CHI-SQUARE A test of statistical significance

Why Hypothesis Testing To determine whether a relationship exists between two variables and did not arise by chance. (Statistical Significance) To measure the strength of the relationship between an independent and a dependent variable? (association)

Things about Chi-Square It is not a test of strength, just significance Chi-square is inflated by large samples It is a test that tries to disprove the null hypothesis. An insignificant chi-square means that no relationship exists.

Chi-Square is an up or down measure If our significance value is less than or equal to.05 table, we reject the null hypothesis- we have a relationship if our Chi-Square value from our test is greater than.05 we accept the null hypothesis and we have no relationship

HOW TO DO IT IN SPSS

An Easy One Dataset- NES 2008 DV= Who08 IV= Race Null- There is no relationship between Race and Vote in 2008 Alternate- African Americans are More likely to Vote for Obama

First Run A Cross Tab Click on Statistics Click on Chi- Square

The Results What does the Chi-Square Tell us? What is the Asymp. Sig here? What do We Do with the null hypothesis? What is the Practical Significance here?

Hard-Line Immigration Policy D.V. Immigration Policy I.V. Hispanic (dichotomous)

The Results What does the Chi-Square Tell us? What is the Asymp. Sig here? What do We Do with the null hypothesis? What is the Practical Significance here?

What do we have Here?

MEASURES OF ASSOCIATION Nominal Variables

Why Measures of Association Chi-Square only tests for significance It does not say how strongly the variables are related We Use a Measure of Association to Do this

A measure of association is a single number that reflects the strength of the relationship

Measures of association for Nominal Variables tell us: Strength of the Relationship The statistical significance of the relationship These go hand in hand

Measures of Association for Nominal Variables Measure of AssociationRangeCharacteristics Lambda may underestimate, but a PRE measure Phi Use for a 2x2 table only and is Chi-square based Cramer's V Chi-square based and the compliment to PHI.

A value of 1.00 means a perfect relationship, a value of.000 means no relationship

Lambda What kinds of variables are needed for Lambda? Lambda ranges from 0 (no relation) to 1 (a perfect relationship) It measures how much better one can predict the value of each case on the DV if one knows the value of the IV

Interpreting Lambda.000 to.10 none weak moderate strong.40 and above- there is a very strong relationship

Reading Lambda in SPSS IN SPSS, LAMBDA GIVES YOU 3 DIFFERENT VALUES Symmetric- always ignore Two measures of your dependent variable – always use the lambda associated with your dependent variable. – If you place the dependent variable as the ROW VARIABLE, this will be the middle value. Help from Rocky IV. And the videoRocky IVvideo

The one in the middle The significance of the Lambda

Lambda as a PRE Measure Proportional Reduction in Error (PRE) this is defined as the improvement, expressed as a Percentage, in predicting a dependent variable due to knowledge of the independent variable. How well we can predict the dependent variable by knowing the independent variable?

Converting a Lambda to a Percent We take the value of our association measure Multiply by 100% this is our PRE value.

SOME LAMBDA PRACTICE EXAMPLES

Problems with Lambda It fears a TYPE I error so it is very conservative Lambda can Underestimate relationships, even when there are significant chi-square values. If the modal category is even, Lambda is pretty useless.

ALTERNATIVES TO LAMBDA Phi and Cramer’s V

Cramer’s V An alternative to Lambda Ranges from Not a Pre Measure

Phi Measured similarly to Lambda You will use this with 2x2 tables only

An Example Here we can say with a.369 Cramer's V, that we have a very strong relationship between our independent and dependent variables.

Phi And Cramer’s V Interpreting them.000 to.10 none weak moderate strong.40 and above- there is a very strong relationship Limitations Neither are PRE Measures They are both Chi-square based so large samples inflate it

Lambda Underestimating

What the Cramer’s V Tells Us If the Modal category is hard to predict, Lambda falls flat What we see is a weak- to-moderate relationship here. Independents and Democrats are different

Lambda Underestimating Part II D.V.- obama_win08 IV- Region

Lambda shows Nothing We have a moderate relationship, but it is not significant (small sample)

RUNNING LAMBDA, PHI AND CRAMER’S V

Easy to Do How to do it in SPSS Analyze – Descriptive Cross-Tabs – Click on the Statistics Tab Highlight your nominal variable statistics – Choose continue

Two Examples Region and Cig Taxes Region and Public Support for Gay Rights